A Python implementation of Farasa toolkit
-
Updated
Sep 11, 2025 - Python
A Python implementation of Farasa toolkit
Yorùbá language training text for NLP, ASR and TTS tasks
Benchmark Arabic text diacritization dataset
Extensible DL-based automatic Arabic diacritization tool allowing the restoration of different types of diacritics.
Automatic Arabic diacritics restoration tool.
Arabic deep-learning based diacritization models (Shakkala, Shakkelha) ported to PyTorch
Arabic deep-learning based diacritization models (Shakkala, Shakkelha) in the ONNX format.
Course Project for Natural Language Processing
Translation-over-Diacritization technique implementation
Neural Arabic text diacritization website
Lightweight Arabic diacritization (tashkeel) — a model picker over bundled ONNX models, no PyTorch, no network
Arabic diacritization with Transformers
🕌 High-quality Arabic (MSA/Fusha) professional-male TTS — XTTS v2 fine-tune with CATT diacritization, ASR-based evaluation (human-level CER), and a streaming FastAPI service.
Arabic diacritization engine achieving 2.29% DER and 99.997% Quran accuracy in 6.7 MB — 62x smaller than SOTA
Reproduction of the released CATT Arabic diacritization ED on the public held-out split: configs, scorers, committed results
Fine-tuned CANINE for restoring Persian diacritics (harakat) at the character level
Arabic diacritization (tashkeel) with a 1.08 M parameter character Transformer: full training pipeline, evaluation harness, published weights (PyTorch + ONNX), and Gradio/static demos
TantaArabNLP at KSAA-2026: Adapting CATT-Whisper for Arabic Speech Dictation with Automatic Diacritization.
Tonalizer - CRF-based Tone Reconstitution Tool
To associate your repository with the diacritization topic, visit your repo's landing page and select "manage topics."